kaBEDONN: posthoc eXplainable Artificial Intelligence with Data Ordered Neural Network

Erico Tjoa, Cuntai Guan

Keywords: Explainable Artificial Intelligence, Neural Network, instance-based learning

TL;DR: A posthoc method for providing explanation to blackbox algorithms by querying similar data

Abstract: Different approaches to eXplainable Artificial Intelligence (XAI) have been explored including (1) the systematic study of the effect of individual training data sample on the final model (2) posthoc attribution methods that assign importance values to the components of each data sample. Combining concepts from both approaches, we introduce kaBEDONN, a system of ordered dataset coupled with a posthoc and model-agnostic method for querying \textit{relevant} training data samples. These \textit{relevant} data are intended as the explanations for model predictions that are both user-friendly and easily adjustable by developers. Explanations can thus be finetuned and damage control can be performed with ease.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning